Abstract
The data processing of airborne full-waveform light detection and ranging (LiDAR) systems has become a research hotspot in the LiDAR field in recent years. However, the accuracy and reliability of full-waveform classification remain a challenge. The manual features and deep learning techniques in the existing methods cannot fully utilize the temporal features and spatial information in the full waveform. On the premise of preserving temporal dependencies, we convert them into Gramian angular summation field (GASF) images using the polar coordinate method. By introducing spatial attention modules into the neural network, we emphasize the importance of the location of texture information in GASF images. Finally, we use open source and simulated data to evaluate the impact of using different network architectures and transformation methods. Compared with the performance of the state-of-art method, our proposed method can achieve higher precision and F1 scores. The results suggest that transforming the full waveform into GASF images and introducing a spatial attention module outperformed other classification methods.
Funder
Guangxi Innovative Development
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference31 articles.
1. Relation network for full-waveforms lidar classification;Guiotte;ISPRS-Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci.,2020
2. Airborne small-footprint full-waveform LiDAR data for urban land cover classification;Qin;Front. Environ. Sci.,2022
3. A Multi-Source Convolutional Neural Network for Lidar Bathymetry Data Classification;Zhao;Mar. Geod.,2022
4. Island feature classification for single-wavelength airborne lidar bathymetry based on full-waveform parameters;Ji;Appl. Opt.,2021
5. Shanjiang, H., Yan, H., Bangyi, T., Jiayong, Y., and Weibiao, C. (2019). Classification of sea and land waveforms based on deep learning for airborne laser bathymetry. Infrared Laser Eng., 48.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献